How The Amarna Mysteries Are Made

The Amarna Mysteries is written with the assistance of artificial intelligence. That sentence answers the least interesting question anyone asks about the series. The questions worth asking — the ones a serious reader, a journalist, or a publisher actually has — are these: who was in charge, and how was quality controlled?

The answer is a human author running a verification-first authorship and editorial process, one that treats every AI output as a candidate, never a verdict. This page describes that process and the model behind it.

The Amarna Mysteries is AI-assisted and human-authored.

AI systems were used to help generate first-draft material, propose revisions, summarize complex material, test continuity, challenge historical plausibility, review prose texture, and compare alternatives. That does not mean the books were autonomously written by AI. It means AI-generated material entered a human-directed authorship and editorial process.

I work under what I think of as a Project Director model. The human author remains the creative, editorial, and canon authority. AI systems are not treated as co-authors, ghostwriters, or autonomous decision-makers. They are specialist assistants. Their outputs are candidates, not verdicts.

The center of the system is not a chat session. It is the project documentation: the Series Bible, change logs, operating records, chapter files, and version history. The Series Bible governs the canon — names, dates, relationships, chronology, historical interpretation, language rules, and settled creative decisions. AI tools answer to that authority; they do not create it.

This matters because a long historical mystery series cannot be safely governed by memory, enthusiasm, or a single AI conversation. A detail in one chapter may affect a relationship, a timeline point, a historical claim, a clue, or a reader payoff several books later.

The workflow therefore separates kinds of assistance. Drafting support is different from continuity review. Historical plausibility is different from prose texture. Structural challenge is different from canon authority. No single tool or model is treated as sufficient.

AI can be useful, but it is not infallible. It can miss real problems. It can also invent problems that are not in the text. For that reason, AI output is treated as raw material for human judgment. Findings are checked. Drafts are revised. Suggestions are rejected when they do not serve the book.

The final manuscript reflects human selection, rewriting, arrangement, verification, and approval. I take responsibility for the final expressive form of the work.

The purpose of the system is not to make AI sound authoritative. It is to make AI interruptible, checkable, and subordinate to human judgment.

The books were edited under a written operating procedure in which separate AI systems were each assigned a limited function, deliberately unable to substitute for one another.

A continuity review tests the manuscript against the Series Bible and against itself. A historical plausibility review tests the book's world against a closed, author-curated corpus of Egyptology — insulated from the fiction, so it can never validate the novel against itself. A prose-texture review works on the surface of the writing, instructed to flag facts but never change them. A structural challenge audits the draft against a locked story model.

Above all of these sits a human-maintained Series Bible: the single canonical authority on every name, date, relationship, and fact in the series. The AI assistants answer to it, never the other way around.

AI checking tools are unreliable in both directions: they miss real errors, and they fabricate convincing ones — complete with quoted text that exists nowhere in the manuscript. This project documented those failure modes as they occurred and built the process around them.

Every finding from every tool was verified against the actual text before any action was taken. A literal text search is the ground truth; the tool's verdict is only ever a candidate. Fact-level changes — names, dates, ages, historical claims — were never applied automatically; each one was a human decision. And the final gate was not a tool at all: the author's complete pre-publication read of the locked text.

The methodology assumes AI tools will sometimes be wrong, and is built so that their errors are caught before they reach the reader. That is the difference between using AI and being used by it.

The series is built against the archaeological and textual record of the late 18th Dynasty, with research run against author-curated scholarly sources. Where the story deliberately departs from mainstream Egyptology, those departures are documented decisions, not accidents.

The scholarship that provides the foundation is surveyed in The Amarna Period: Egypt's Most Volatile Decade and acknowledged in the front matter of each book as it publishes.

Characters, plot, and voice originate with the author. The choice of which scholarly interpretation to follow when the evidence is disputed is a human decision. What Nefertiti would say, think, or do in a given scene is a human decision. Every scene, chapter, and line of dialogue in the published books reflects human authorial judgment.

The author claims authorship of the original plot and narrative structure of each novel; the characterization and arcs of all named characters; the selection, coordination, and arrangement of all textual content; the integration of historical and archaeological research into fiction; the chapter architecture and scene sequencing; and all substantive creative revisions throughout the manuscripts. Individual AI-generated sentences and paragraphs, as such, are not claimed as protectable expression; the human-authored selection, coordination, arrangement, and creative modification of the work as a whole is.

In the language of U.S. Copyright Office guidance, the human author retains copyright in the original expression of the work and in the creative selection, coordination, and arrangement of all material — whether that material was drafted from scratch, modified from an AI suggestion, or composed in dialogue with the AI tools described above. The framework set out in the Office's January 2025 report on copyrightability and AI is the framework this project operates within.

The series is AI-assisted and human-authored. AI systems were used to help generate draft material, propose edits, test continuity, challenge historical plausibility, and review prose. Those outputs were not treated as finished authorship. I selected, rejected, rewrote, rearranged, verified, and approved the final text. The Series Bible governs canon, chronology, character relationships, historical interpretation, and language rules.

Every book in the series carries the same standing historical-fiction disclaimer:

"The characters in this novel are based on historical figures of Egypt's Eighteenth Dynasty (c. 1332–1323 BCE). While the setting, people, and broad political circumstances are drawn from the archaeological and textual record, their private thoughts, dialogue, and specific actions within these pages are works of imagination. Where the historical record is silent, the author has listened carefully before speaking."

This approach was developed through practice and refined across the production of a four-book series. AI tools, used within a disciplined framework and directed by experienced human judgment, contribute meaningfully to the production of serious historical fiction. The work itself is the evidence: The Amarna Mysteries.

The author is responsible for the content of the published novels and for the accuracy of this methodology disclosure. Questions regarding the methodology may be directed to aj@theamarnamysteries.com.

A.J. Tilke is the author of The Amarna Mysteries, a four-book historical fiction series set in ancient Egypt's 18th Dynasty. The Poisoner's Throne (Book 1) will publish in August 2026, followed by The Restoration Trilogy — The Hittite Reckoning, The Restoration Murders, and The Dakhamunzu Affair — later in 2026. A short-story anthology, The Twelve Hours of Night, is planned for 2027.